AI Agent Engineer

Blue Machines AI; Chennai District; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Blue Machines AI is building production Voice AI for India's largest enterprises, delivering live conversations in Hindi, Hinglish, and regional languages. You design, build, integrate, and debug the AI agent end-to-end, taking ownership of delivery rather than handing off to a partner.

You will own conversation design, tool-calling logic, and end-to-end debugging while collaborating with clients to explain issues, set timelines, and improve agent funnels through experiments and data-driven

Qualifications

• 5+ years of hands-on experience shipping an LLM/AI feature touching real users
• Able to read a log or trace and reason whether an issue is prompt, platform, or data
• Comfortable pulling data in SQL, Sheets, or Python
• Fluent English and Hindi
• Willing to travel for client workshops and live-call reviews
• Comfortable in front of clients — can explain a technical issue in plain terms and manage expectations

Responsibilities

• Conversation design, prompts, guardrails, and tool-calling logic
• Basic integrations (webhooks, CRM writes, callbacks) your agent depends on
• Debugging: diagnose whether an issue is prompt, platform, or data
• Evaluation and iteration: track hallucination rate, completion rate, latency, cost
• Experiments on your agent's funnel with defined success metrics
• Client-facing calls on your agent: explain issues and set realistic timelines

Skills

Conversation design

Client communications

Problem solving

Multilingual communication

Project delivery

Tools

SQL

Sheets

Python

Job description

Location: Mumbai (1 position) , Chennai (2 positions)

Experience: 5+ years

Blue Machines builds production Voice AI for India's largest enterprises — millions of live conversations in Hindi, Hinglish, and regional languages. You design, build, integrate, and debug the AI agent end-to-end. You are delivery for your agent, not a partner handing off to it.

You'll Own

• Conversation design, prompts, guardrails, and tool-calling logic
• Basic integrations (webhooks, CRM writes, callbacks) your agent depends on
• Debugging: given a bad call, prove whether it's prompt, platform, or data — not guess
• Evaluation and iteration: hallucination rate, completion rate, latency, cost
• Experiments on your own agent's funnel (opening line, retry cadence, sequencing) with a defined success metric
• Client-facing calls on your agent: explain what broke, what you're doing about it, and set realistic timelines

Must Have

• 5+ years of experience, with hands-on work shipping an LLM/AI feature real users touched — chatbot, RAG, or agent (voice a plus, not required)
• Can read a log or trace and reason whether an issue is prompt, platform, or data
• Comfortable pulling your own data in SQL, Sheets, or Python
• Fluent English and Hindi
• Willing to travel for client workshops and live-call reviews
• Comfortable in front of clients — can explain a technical issue in plain terms and manage expectations without becoming defensive.

Good to Have

• Tamil, Telugu, Kannada, Malayalam, Marathi, or Gujarati
• BFSI/lending exposure

Non-Ideal Fit

• Ship-and-forget builders uninterested in monitoring or RCA
• Spec-writers who don't build

Process

Screen → live take-home (build + deploy a working voice agent) → deep-dive on what you built → final conversation. The take-home is the real gate on voice-specific skill — not the resume.