Apply with hirly
Software Developer
KNOLSKAPE · Bengaluru, India
Upload your resume to see how well you match this job — free, in seconds, no account needed.
Your resume is used only to score it against this job. If you don't create an account, it is deleted within 24 hours.
What You'll Do
- Build Gen-AI product features
- Design and ship agentic workflows that turn author briefs into simulations, roleplays, assessments, and coaching experiences
- Engineer for production
- Write robust TypeScript services and APIs; handle streaming, latency, cost, rate limits, failure modes, and observability for LLM-backed features
- Develop AI agents
- Build and orchestrate multi-step agents (planning, tool use, structured outputs, guardrails) that generate and refine learning content reliably
- Evaluate and iterate
- Build evals and feedback loops to measure generation quality, catch regressions, and improve prompts/agents systematically
- Collaborate and communicate
- Work with product managers, learning designers, and fellow engineers; write clear design docs, articulate trade-offs, and present your work
- Stay current
- Track the fast-moving Gen-AI landscape (models, agent frameworks, retrieval techniques) and bring the best of it into KNOLSKAPE's products What We're Looking For Must-Have
- 2+ years of professional software engineering experience , with strong proficiency in JavaScript/TypeScript (Node.js on the backend; React or similar on the frontend is a plus)
- Hands-on Gen-AI experience
- you've shipped features built on LLM APIs (Anthropic, OpenAI, Gemini, or similar), not just experimented in notebooks
- Experience building AI agents
- multi-step orchestration, tool/function calling, structured outputs, and handling the messiness of non-deterministic systems
- Experience with RAG
- embeddings, vector databases (pgvector, Pinecone, or similar), chunking strategies, and retrieval quality tuning
- Strong communication skills
- you can explain technical decisions to non-engineers, write clear documentation, and collaborate effectively across teams
- Product mindset
- you care about what authors and learners experience, not just what the model outputs
- Ownership and self-direction
- you can take an ambiguous problem, scope it, and drive it to a shipped outcome Nice-to-Have
- Experience with agent frameworks (LangChain/LangGraph, Vercel AI SDK, Claude Agent SDK, or hand-rolled orchestration)
- Experience building LLM evals or quality measurement pipelines
- Familiarity with prompt engineering at scale — versioning, templating, A/B testing prompts
- Experience with streaming UX (SSE/WebSockets) for real-time AI interactions
- Exposure to speech/multi-modal AI (TTS, STT, avatar/video generation)
- Experience with cloud platforms (AWS, GCP, or Azure), Docker , and CI/CD
- Background in ed-tech, learning platforms, or other content-generation products