Senior Artificial Intelligence Engineer

The Role We're hiring a Senior AI Engineer to design and ship GenAI features end-to-end from prototype to production. You'll build agentic systems that enterprise customers depend on, and pair closely with our Senior Full Stack Engineer to integrate AI into the product. We're an AI-native engineering team: building with tools like Claude Code and Codex at the center of your workflow isn't a nice-to-have here it's how we work.

Location: Bangalore.

Experience: 3+ years

Role & responsibilities

What You'll Do

• Design and ship GenAI product features end-to-end prototype to production
• Build agentic systems: multi-step workflows, tool use, orchestration, MCP integrations
• Build memory systems for agents short- and long-term memory, context management, knowledge that persists and improves across sessions
• Build RAG pipelines — embeddings, vector stores, retrieval quality tuning
• Own eval harnesses: systematic quality measurement, regression testing, LLM observability
• Optimize for cost, latency, and reliability at production scale
• Implement guardrails for enterprise customers — data privacy, tenant isolation, output safety
• Pair with the full stack engineer to integrate AI into the product

Preferred candidate profile

What We're Looking For

• 3+ years software/ML engineering with production systems; strong Python
• 2+ years building LLM applications in production — not just prototypes
• Strong hands-on experience with LangGraph or similar agent frameworks (CrewAI, AutoGen, OpenAI Agents SDK, Claude Agent SDK) — has built and operated production agentic systems, not just tutorials
• Deep grasp of agentic patterns: tool calling, state management, memory architectures, multi-agent orchestration, human-in-the-loop design
• RAG experience: embeddings, vector DBs, retrieval evaluation
• Experience evaluating LLM systems — building eval datasets, automated scoring, and regression testing for prompt and model changes
• Fluent with AI-assisted development (Claude Code, Codex, Cursor, or similar) — uses these tools agentically to multiply output, not just for autocomplete