Back to all jobs
O
Senior Gen AI Developer
Orion Innovation Naukri
India1mo ago
- Seniority
- Senior
About the role
<p><strong><span style="font-size: 10pt;">Job Overview:</span></strong></p>
<p><span style="font-size: 10pt;">We are looking for a Senior GenAI Developer to design, build, and productionize agentic AI systems—LLM-powered agents that can plan, use tools, orchestrate workflows, and operate reliably under enterprise constraints. You will own key parts of the agent architecture (planning, tool use, memory, evaluation, safety/guardrails, and observability) and deliver end-to-end solutions across RAG, function/tool calling, multi-agent coordination, and scalable deployment.</span></p>
<h2><span style="font-size: 10pt;">Key Responsibilities</span></h2>
<ul>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Design and implement agentic systems: single-agent and multi-agent architectures (planner/executor, supervisor-worker, routing, reflection, critique, task decomposition).</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Build robust tool-using agents: function calling, tool schemas, tool authorization, retries, rate limiting, and sandboxing.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Implement RAG + memory patterns: retrieval strategies, hybrid search, context assembly, long-term memory, and grounding/citation behaviors.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Develop workflow orchestration for agent execution (state machines/graphs), concurrency controls, and deterministic execution where possible.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Productionize GenAI services: APIs, background jobs, streaming responses, caching, and cost/latency optimization.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Establish agent evaluation: golden sets, simulation-based evals, LLM-as-judge with mitigations, task success metrics, regression testing.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Build observability and safety: tracing, token/tool telemetry, anomaly detection, prompt injection defenses, data leakage prevention, policy enforcement.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Collaborate with product, security, and platform teams to deliver enterprise-ready solutions and integrate with internal systems (data, identity, workflow).</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Mentor engineers, set coding standards, and contribute to architecture reviews and technical roadmaps.</span></li>
</ul>
<h2><span style="font-size: 10pt;">Required Qualifications</span></h2>
<ul>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">6+ years software engineering experience; 2+ years building LLM/GenAI systems in production.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Strong programming skills in Python (required) and/or TypeScript/Node.js.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Hands-on experience building agents (tool calling, planning, routing, multi-step workflows) beyond simple chatbots.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Solid understanding of prompting, context window management, grounding, hallucination failure modes, and mitigation strategies.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Experience with RAG: embeddings, vector databases, chunking strategies, hybrid retrieval, re-ranking.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Proven ability to ship production services: Docker/Kubernetes, REST/gRPC, CI/CD, monitoring, incident response basics.</span></li>
<li style="font-size: 10pt;"><span style="font-size: 10pt;">Strong data/security instincts: secrets management, PII handling, secure tool access, least privilege</span></li>
</ul>
<p> </p>
753,000+ hidden jobs like this
Orion Innovation Naukri and thousands of companies post here first — often days before LinkedIn or Indeed. Your first 5 applications are free; go Pro to apply without limits.
Everything Pro unlocks:
- Unlimited applications — free stops at 5
- Track every application in one place
- Apply straight to the source, one click
- Save & organize roles you love
- Roles pulled from company boards before the big sites