Senior Applied AI Engineer

Built In
India
On-site

Who this role is best for

Aimed at experienced AI engineers who have shipped agentic systems and can navigate multi-model intelligence, with a focus on Python and AWS serverless infrastructure in India.

Best fit for

  • Candidates with experience shipping agentic systems and managing non-deterministic outputs in production.
    — “Agentic systems you've shipped to production, for an employer or for customers.”
  • Individuals who can architect and evaluate AI workflows with a human-in-the-loop mindset.
    — “You operate with a human-in-the-loop mindset, using agentic tooling to compress what would traditionally be a team-sized effort into individual throughput.”
  • Professionals familiar with multi-model intelligence and can detect brand hallucinations or sentiment discrepancies.
    — “Develop systems that synthesize outputs from ChatGPT, Gemini, and Perplexity to identify sentiment discrepancies, detect brand hallucinations, and surface actionable intelligence for customers.”

Things to consider

  • The role requires deep familiarity with specific AI model APIs and their integration.
    — “Hands-on work with frontier model APIs from OpenAI, Google, Perplexity or Anthropic, including function calling, structured outputs, and streaming.”
  • Candidates should be prepared to work closely with product teams and ensure AI systems are stateful and observable.
    — “Work closely with Software Engineers and Product Managers to integrate agentic behaviors into production frameworks, ensuring AI systems are stateful, observable, and resilient.”

How to stand out

  • Highlight specific agentic systems you've deployed and how you ensured reliability.
    — “Please describe one or two agentic systems you've shipped.”
  • Demonstrate your ability to handle unpredictable model outputs and failure scenarios.
    — “How you handled failures, state or unpredictable model output.”
  • Showcase your experience in building evaluation frameworks for agent systems.
    — “Evaluation you've built and relied on. Custom evaluation frameworks such as LLM-as-a-Judge, trace-based testing and regression suites.”
Pace · Fast PacedCollaboration · HighAutonomy · MediumDecision Impact · Team

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

  • Architect Agentic Systems
  • Operationalize Agents in Production
  • Evolve Multi-Model Intelligence
  • Build Scalable Cloud Infrastructure
  • Drive Evaluation and Quality
Typical background
5+ years of professional software engineering experienceExperience with AI and machine learning

Skills & requirements

Required

Agentic SystemsProduction-grade Agentic WorkflowsReflectionSelf-correctionPlanningMulti-agent OrchestrationLlm-as-a-judge Evaluation FrameworksTrace-based Testing PipelinesQuality Feedback LoopsServerless Backend ServicesPythonAWS LambdaObservabilityChatgptGoogle GeminiPerplexity

Preferred

Production Agentic SystemsHuman-in-the-loop Mindset

Stack & domain

PythonAWS LambdaChatgptGoogle GeminiPerplexityServerless Backend ServicesLlm-as-a-judge Evaluation FrameworksTrace-based Testing PipelinesAITech

About the role

Original posting from Built In via Greenhouse

Hello, We’re Built In

What We’re Up To 

We’re building the largest platform for tech professionals globally. Monthly, millions of professionals visit BuiltIn.com from across the world. We’re the only platform they need to stay ahead of tech trends and news, develop their careers and find opportunities at companies they believe in.

Our 1,800 customers include innovative companies of all sizes, from exciting startups to companies in the Fortune 100. To attract our audience of skilled professionals, they trust us to tell the stories of their cultures and share their job opportunities. This helps them hire the industry’s most sought-after professionals locally, nationally and remotely – ultimately contributing to the industry’s ability to innovate a better future.

What You’ll Be a Part Of Working at Built In is the chance to help shape a fast-growing company. With venture funding of $30 million to date, we’re expanding not just our geographic footprint but our products and technology. You’ll also be a part of changing the lives of professionals like you, ambitious people with a passion for tech and love of learning. As a result, you’ll understand the impact of your work in a deeply personal, especially meaningful way.

About the Role

We are looking for an Applied AI Engineer to design and build the autonomous systems that power Built In’s product suite. Our platform already generates deep analytical insights for customers—your job is to build the Agentic Action Layer that turns those insights into outcomes. You will create multi-agent systems that don’t just surface data but take intelligent, supervised action across the major AI frontiers: ChatGPT, Google Gemini, and Perplexity.

The ideal candidate has already shipped production agentic systems and knows where orchestration frameworks help versus where they get in the way. You operate with a human-in-the-loop mindset, using agentic tooling to compress what would traditionally be a team-sized effort into individual throughput—without sacrificing reliability.

How You’ll Contribute

Architect Agentic Systems: Design and implement production-grade agentic workflows—including Reflection, Self-Correction, Planning, and Multi-Agent Orchestration patterns—to power a growing portfolio of AI-driven product capabilities.

Operationalize Agents in Production: Own the full lifecycle from rapid prototype to production deployment. Build agent systems with real-world constraints in mind: token budgets, latency targets, graceful degradation, and cost observability.

Evolve Multi-Model Intelligence: Develop systems that synthesize outputs from ChatGPT, Gemini, and Perplexity to identify sentiment discrepancies, detect brand hallucinations, and surface actionable intelligence for customers.

Build Scalable Cloud Infrastructure: Design and maintain serverless backend services using Python and AWS Lambda, ensuring agents perform efficiently at scale with proper observability.

Drive Evaluation and Quality: Build LLM-as-a-Judge evaluation frameworks, trace-based testing pipelines, and quality feedback loops that keep agent output reliable as models and prompts evolve.

Collaborate Across Teams: Work closely with Software Engineers and Product Managers to integrate agentic behaviors into production frameworks, ensuring AI systems are stateful, observable, and resilient.

What You Bring

5+ years of full-time professional software engineering experience. Internships, training programs and academic projects are valuable but don't count toward this.

Agentic systems you've shipped to production, for an employer or for customers. Patterns like ReAct, Planning, Reflection, and Multi-Agent Orchestration. You've moved agents from demo to production and dealt with the hard parts: failure handling, state management, and non-deterministic outputs.

Evaluation you've built and relied on. Custom evaluation frameworks such as LLM-as-a-Judge, trace-based testing and regression suites, used to keep agent output quality up over time. You understand that the hardest part of production agents isn't building them. It's knowing when they're wrong.

Hands-on work with frontier model APIs from OpenAI, Google, Perplexity or Anthropic, including function calling, structured outputs, and streaming.

Strong Python for AI orchestration.

Strongly Preferred

Working knowledge of C# / .NET. Our core platform runs on .NET, and you'll integrate your agent systems with it, not just work alongside it.

Production experience with AWS serverless (Lambda, Step Functions, EventBridge) for high-frequency, agentic workloads.

Power user of agentic developer tools (e.g., Claude Code, Cursor, or custom agentic CLI workflows). You use them to architect, refactor, test, and ship, not just autocomplete, and you can manage multiple agents across a codebase with minimal manual intervention.

What to Include in Your Application

We read every application for specifics. Please describe one or two agentic systems you've shipped:

What the system did, and who used it (users, scale or volume).

Your role in building it.

How you handled failures, state or unpredictable model output.

How you evaluated it and knew when it was going wrong.

What We Value

We’re revolutionizing tech recruitment. So we question everything, because the best answers sit just to the right of a question mark. If you join Built In, you will work from this set of values:

Be Inclusive, Always. * Be Unreasonably Passionate. * Be Humble. * Stay Curious. * Lead with Solutions. * Own the Result. * Do More. ---

Be Inclusive, Always

Research shows that women and other marginalized groups tend to apply to roles only when they check every point on a job description. We encourage you to apply if you meet the majority of qualifications and this role is aligned with your career trajectory.

Built In is an equal employment opportunity employer. Qualified candidates are considered for employment without regard to race, religion, gender, gender identity, sexual orientation, national origin, age, military or veteran status, disability, or any other characteristic protected by applicable law.

Built In is guided by principles of diversity, equity and inclusion (DEI). We are committed to this work over the long-term, but here’s some of what’s in place today:

We have five thriving ERG groups: Built In For The People, BuiltOut, United We Parent, Women United in Tech and Built In Tribe.

We have a dedicated Director, HR + Inclusion who oversees our DEI roadmap.

We are proud to be led by a woman CEO and founder, and that more than half of our managers and employees identify as women.

NOTE: BUILT IN NEVER CONTACTS JOB APPLICANTS VIA TEXT, MESSENGER OR OTHER SIMILAR APPLICATIONS. ONLY RESPOND TO EMAILS FROM BUILTIN.COM.

Source: Built In careers (Greenhouse)

Similar roles