Software Engineer

About the Company

At our core, we are an AI-powered entertainment company with a deeply human-first philosophy. We believe technology should amplify creativity. Our proprietary AI systems work alongside writers, voice artists, and creative teams to help stories scale globally, faster, smarter, and with cultural depth and emotional integrity intact.

Today, Pocket FM is home to a vibrant community of 250+ million listeners, 300,000+ creators, and 100,00+ audio series. With over 140 billion minutes streamed annually, we have emerged as one of the fastest-growing media-tech companies in the world, and we are just getting started. We operate at a massive global scale, but with a startup mindset: curious, fast-moving, and deeply owner-driven.

At Pocket FM, teams are encouraged to think boldly, move with intent, and build for long-term impact as we shape the future of audio-first storytelling worldwide

Our unique model combines free listening with micropayments for premium content, powering strong business growth. In FY25, we reached an ARR of INR 2,000 crore, with over 100,000 hours of content on the platform. We're also at the forefront of innovation, leveraging AI-generated content to scale efficiently.

About the Role

AI Engineer 1

What you will do

• Build agentic systems: Implement agent loops, tool calling, routing, memory, guardrails, state management, and streaming using modern agentic frameworks.
• Build RAG systems: Develop retrieval pipelines covering chunking, embeddings, vector and hybrid search, reranking, graph retrieval, and context packing.
• Improve prompting and context engineering: Write and optimize prompts, tool instructions, context strategies, and memory to improve response quality, reliability, and efficiency.
• Work with LLM models: Integrate and experiment with different models and providers, comparing quality, latency, reliability, and token cost.
• Build AI evaluations: Develop evaluation datasets, test cases, retrieval and generation quality checks, and regression tests to identify issues before they reach users.
• Develop end-to-end AI features: Own assigned AI capabilities from implementation and testing through deployment, monitoring, and iteration.
• Debug AI applications: Investigate agent failures, retrieval misses, unexpected token usage, latency issues, and other AI-related problems; implement fixes and prevent recurring issues.
• Build scalable AI services: Develop Python services using async APIs, databases, background jobs, observability, and production-grade testing.
• Collaborate with product and engineering teams: Translate requirements into reliable AI features, participate in design and code reviews, write technical documentation, and share learnings.
• Continuously improve AI systems: Experiment with new LLM capabilities, agentic approaches, and retrieval techniques; evaluate results and iterate based on measurable improvements.

Required

• 2+ years of total software engineering experience, including hands-on experience building applications using LLMs.
• Strong Python fundamentals and experience building APIs, writing tests, and working with asynchronous or background processing systems.
• Hands-on experience with LLMs, prompt engineering, context engineering, and at least one agentic framework or tool-calling workflow.
• Practical experience building RAG pipelines using embeddings, vector search, retrieval, and context assembly.
• Understanding of relational databases and familiarity with vector databases; exposure to graph databases is a plus.
• Experience evaluating LLM outputs, writing test cases, and debugging quality issues in AI applications.
• Understanding of quality, latency, reliability, and token-cost trade-offs when building LLM-powered features.
• Strong problem-solving skills and the ability to take ownership of assigned tasks, work through ambiguity, and deliver reliable solutions.
• Ability to collaborate effectively with product and engineering teams and communicate technical decisions clearly.
• Curiosity and willingness to learn new AI frameworks, model capabilities, and production engineering practices.

Good to have

• Experience building and shipping an agentic or multi-step tool-using application.
• Familiarity with SSE or streaming LLM responses.
• Experience with hybrid search, reranking, graph-based retrieval, or advanced retrieval strategies.
• Exposure to LLM evaluation frameworks, golden datasets, and automated regression testing.
• Experience with production observability, tracing, and debugging LLM applications.
• Familiarity with async Python frameworks, distributed systems, and cloud-based AI services.
• Experience working with multiple LLM providers and implementing model integrations.