AI Lead, Agentic Development

About Company:

HJ Software Private Limited is a software company that provides innovative, customized web-based solutions to small and medium enterprises. Our offshore development team has a proven track record in delivering web-related solutions on schedule and within budget, to clients of various industries.

AI Lead, Agentic Development

About the role

• Experience: 6+ years in software engineering, including 4+ years hands-on in AI/ML and LLM-

based systems

• Location: Remote / Hybrid

• Employment type: Full-time

We are looking for a hands-on AI Lead who still writes production code every day. You will lead our

agentic development team, build AI agents that solve real business problems, and train other teams

across the company to use AI effectively.

This is not a slides-and-strategy role. You will architect, code, test, deploy and support the systems you

design, and set the engineering bar for the team.

What you will do

Agentic development

• Architect, code and ship production AI agents end to end: tool design, orchestration, memory,

error handling, deployment and monitoring.

• Build and own the shared agent platform: model access, connectors to business systems,

secrets, logging, tracing and cost tracking.

• Write high-quality, tested production code and lead by example in code reviews.

• Build evaluation pipelines from real data, set accuracy targets and block releases that miss

them.

• Design guardrails: what agents can do on their own, what needs human approval, and how

every action is audited.

• Optimise agents for latency, cost and reliability at scale.

• Set standards for using AI coding agents in software delivery: repo setup, review, testing and

CI/CD.

• Partner with business teams to find, scope and measure high-value AI use cases.

Training and enablement

• Design and run an AI training program for engineering and non-technical teams.

• Lead hands-on workshops, demos and office hours on AI tools, prompting, agents and safe use.

• Create playbooks, reusable prompt libraries and best-practice guides.

• Build and support a network of AI champions across departments.

• Mentor AI developers and engineers, and grow the team’s technical depth.

What you bring

Must have

• 6+ years of professional software engineering, with 4+ years hands-on building AI/ML or LLM-

based systems.

• Expert coding skills in Python, plus at least one of TypeScript, C#, Java or Go. You write clean,

tested, production-grade code daily.

• Strong computer science fundamentals: data structures, algorithms, system design, concurrency

and performance.

• Production experience with LLM APIs (e.g. Claude, OpenAI), tool/function calling, structured

outputs and multi-step agent workflows.

• Hands-on with agent frameworks and protocols (e.g. LangGraph, Claude Agent SDK, MCP) and

knowing when to build your own.

• Built RAG systems: embeddings, vector databases, chunking, retrieval tuning.

• Designed and run LLM evaluation pipelines and regression testing.

• Strong cloud experience (Azure, AWS or GCP): serverless, containers, identity, secrets and

monitoring.

• Deep experience with REST APIs, event-driven systems and integrating third-party platforms.

• Strong engineering discipline: Git, code review, automated testing, CI/CD, infrastructure as code.

• Daily use of AI coding agents (e.g. Claude Code, Cursor, GitHub Copilot).

• Proven experience mentoring engineers and training or presenting to technical and non-

technical audiences.

Nice to have

• Led a small or distributed engineering team.

• Fine-tuning, model hosting or open-source model deployment.

• Document processing, OCR or classification at scale.

• Integration with CRM, ERP or other enterprise platforms.

• • Open-source contributions or a public portfolio of AI projects.