Location: India

Team: Engineering

Type: Full-time

About the Role

We’re looking for a hands-on AI engineer who can do a bit of everything. You’ll build LLM-powered applications, write and test prompts, connect APIs, and get everything running in production. This includes setting up the infrastructure, managing deployments, and making sure things stay fast and reliable.

You’ll be part of a small team building real-world AI products for healthcare and pharma—where accuracy, speed, and stability matter. We move quickly, ship often, and value people who can take ownership from idea to production.

What You’ll Do

• Build end-to-end LLM applications: prompt engineering, chaining, retrieval, evals
• Deploy and maintain LLM agents in production (low-latency, high-availability infra)
• Design and manage infrastructure
• Fine-tune voice experiences (speech-to-text, text-to-speech, streaming APIs)
• Optimize for speed, reliability
• Collaborate directly with founders to turn ambiguous ideas into polished systems
• Experiment rapidly and own your stack end-to-end

What We’re Looking For

• 2–3+ years of experience in software/ML/infra roles
• Strong Python (bonus: TypeScript or Go), API development, systems + architecture thinking
• Experience building with OpenAI/Anthropic/LLM APIs