Lead Software Engineer

About the Role

As a Lead Software Engineer, you are a strong systems thinker who can be hands-on with critical designs but primarily multiplies your impact by ensuring abstractions and standards stick across the organization. You will be at the forefront of integrating Generative AI into our core product, leading a micro-team to build scalable, resilient, and highly autonomous agentic workflows that solve real-world problems.

Roles and Responsibilities:

• System Design & Execution: Think big but execute with great focus. Adopt a milestone-based approach over "big bang" releases to ship high-impact features iteratively.

• Design for Scale & AI: Design and code with scale, high availability, and cost-efficiency in mind—carefully balancing traditional cloud compute costs with LLM latency and token economics.

• Agentic Orchestration: Own problem statements from end to end, building abstractions that allow LLM agents to plan, call tools, and complete complex tasks safely in production.

• Leadership & Mentorship: Lead a micro-team, driving the adoption of excellent tech processes, evaluation frameworks, and deployment tools. Mentor fellow colleagues and elevate the team's code quality through rigorous reviews.

• Tech Stack Agility: Remain open and adaptable to working across a polyglot tech stack, bridging the gap between standard backend systems and AI ecosystems.

Requirements:

Core Engineering & Tech Stack:

• 4-7 years of proven experience building scalable distributed systems and RESTful Web Services.

• Languages: Expertise in the Java programming language and frameworks, alongside a strong familiarity with Python and its related frameworks.

• Data & Messaging: Hands-on experience with MongoDB, ElasticSearch, Scylla, Redis, and Kafka.

• Big Data & Analytics: Experience with data processing frameworks and query engines like Apache Spark or AWS Athena.

• Orchestration & Task Frameworks: Familiarity with workflow orchestration and task queue frameworks like Apache Airflow or Celery.

• Infrastructure: Familiarity with Linux environments and at least one major cloud computing infrastructure (GCP / Azure / AWS).

• Security: Strong awareness of Secure Development Lifecycle (SDLC) processes and Information Security best practices (including AI-specific security like mitigating prompt injection).

• Ownership: High accountability and a proven track record of taking total ownership of the modules and microservices you build.

Agentic & AI Expertise:

• Agentic Workflows: Proven track record of building and shipping agentic systems that do real work (multi-step planning, dynamic tool calling, autonomous task completion) in production environments.

• Tooling Protocols: Experience designing and managing a "tool-bus" or integrating with protocols like the Model Context Protocol (MCP) to safely and securely expose product skills to an LLM runtime.

• LLMOps & Evaluation: Mastery in setting up evaluation harnesses (golden sets, regressions), tracing tool failures, and strictly tracking LLM cost/latency under real-world traffic constraints.

• Model Tuning & Safety: Hands-on experience deciding when to fine-tune vs. prompt engineer, safely building domain training data, and monitoring tuned models in production for quality and safety regressions.