Gen AI Developer/ Senior Developer

Orion Innovation; Chennai District; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

Orion Innovation is seeking a Senior GenAI Developer to design and productionize LLM-powered AI systems. You will be responsible for key aspects of the agent architecture, including planning, tool use, and robust deployment strategies.

The ideal candidate has over 3 years of experience in software engineering, with strong programming skills in Python and experience in developing complex agentic systems. This role offers significant opportunities for impact in a rapidly evolving environment.

Qualifications

• 3+ years in software engineering with expertise in building LLM/GenAI systems in production.
• Strong programming skills in Python and/or TypeScript/Node.js.
• Experience building agents beyond simple chatbots.

Responsibilities

• Design and implement agentic systems: single-agent and multi-agent architectures.
• Build robust tool-using agents with function calling and tool schemas.
• Productionize GenAI services, ensuring cost and latency optimization.

Skills

Python

TypeScript/Node.js

Building LLM/GenAI systems

Tool calling

Multi-step workflows

RAG

Tools

Docker

Kubernetes

REST/gRPC

Job description

Job Overview

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.

Key Responsibilities

• Design and implement agentic systems: single‑agent and multi‑agent architectures (planner/executor, supervisor‑worker, routing, reflection, critique, task decomposition).
• Build robust tool‑using agents: function calling, tool schemas, tool authorization, retries, rate limiting, and sandboxing.
• Implement RAG + memory patterns: retrieval strategies, hybrid search, context assembly, long‑term memory, and grounding/citation behaviors.
• Develop workflow orchestration for agent execution (state machines/graphs), concurrency controls, and deterministic execution where possible.
• Productionize GenAI services: APIs, background jobs, streaming responses, caching, and cost/latency optimization.
• Establish agent evaluation: golden sets, simulation‑based evals, LLM‑as‑judge with mitigations, task success metrics, regression testing.
• Build observability and safety: tracing, token/tool telemetry, anomaly detection, prompt injection defenses, data leakage prevention, policy enforcement.
• Collaborate with product, security, and platform teams to deliver enterprise‑ready solutions and integrate with internal systems (data, identity, workflow).
• Mentor engineers, set coding standards, and contribute to architecture reviews and technical roadmaps.

Required Qualifications

• 3+ years in software engineering with deep expertise in building LLM/GenAI systems in production.
• Strong programming skills in Python (required) and/or TypeScript/Node.js.
• Hands‑on experience building agents (tool calling, planning, routing, multi‑step workflows) beyond simple chatbots.
• Solid understanding of prompting, context window management, grounding, hallucination failure modes, and mitigation strategies.
• Experience with RAG: embeddings, vector databases, chunking strategies, hybrid retrieval, re‑ranking.
• Proven ability to ship production services: Docker/Kubernetes, REST/gRPC, CI/CD, monitoring, incident response basics.
• Strong data/security instincts: secrets management, PII handling, secure tool access, least privilege.

Orion is an equal opportunity employer, and all qualified applicants will receive consideration for employment without regard to race, color, creed, religion, sex, sexual orientation, gender identity or expression, pregnancy, age, national origin, citizenship status, disability status, genetic information, protected veteran status, or any other characteristic protected by law.