Kantiv•2h ago
LinkedIn
Senior Software Engineer
India
Senior Level
Full Job Description
About this Role: We are seeking a strong Software Engineer with roughly 4–5 years of experience to play a central role in our Chat & Agent Systems team. You will shape technical direction, own system design for day-to-day projects, maintain high engineering quality standards, and mentor junior developers.
Key Responsibilities
- Own the full lifecycle of chat-team project designs and delivery from requirements to implementation.
- Turn product requirements into simple, maintainable system designs that reduce complexity without over-engineering.
- Write production-grade Python code closely involved in final implementation details.
- Create useful abstractions while keeping systems understandable for the team.
- Review pull requests rigorously for correctness, test coverage, and design quality.
- Mentor junior developers to strengthen their programming fundamentals and system-design judgment.
- Diagnose production issues across application code, agent workflows, prompts, models, data, and infrastructure.
- Improve reliability, observability, latency, and cost-efficiency of our chat systems.
Required: Agentic Systems & LLM Expertise
You must have hands-on experience building Large Language Model (LLM) or agentic applications. Relevant background includes:
- Building tool-calling and multi-step workflows using LangGraph or comparable frameworks.
- Designing conversation state, context management, and execution flows.
- Working with model APIs, structured outputs, retrieval-augmented generation (RAG), and grounding data.
- Supporting streaming responses and asynchronous execution patterns.
- Evaluating prompts, models, and end-to-end agent behavior to ensure robustness.
- Instrumenting LLM applications using observability platforms like Langfuse or LangSmith.
Required: Agentic Coding Workflows
The candidate must be a power user of agentic coding workflows, utilizing AI agents as engineering tools for exploration, planning, implementation, testing, debugging, and review. You should:
- Provide effective context, constraints, and verification steps to agents.
- Critically evaluate generated code for security, correctness, and maintainability.
- Design workflows that keep engineers accountable for final output quality.
- Teach junior developers how to use coding agents without compromising engineering fundamentals.
What Success Looks Like
- The team makes clearer, more consistent technical decisions and projects feature simple designs with well-defined boundaries. Code reviews catch meaningful design issues early; production issues are easier to diagnose.
- Juniors receive actionable guidance and grow into independent contributors.
Company
Kantiv
Kantiv (formerly Joist AI) is a pursuit intelligence platform designed for AEC marketing and business development teams.Core Value PropositionWe transform your firm's institutional knowledge—including...
India
Posted on LinkedIn