Lead Software Engineer - AgenticAI

Description and Requirements

• Build and evolve agentic AI systems that reason, plan, execute, and adapt in production environments.
• Lead AI driven features from concept to production in a true 0–1 product environment.
• Write and review high quality production code (Python first) across AI pipelines, inference services, orchestration layers, and supporting systems.
• Implement prompt engineering, tool use, memory, evaluation, and guardrails as first class engineering concerns, not experiments.
• Contribute to the design of agent frameworks that balance autonomy with determinism, observability, and safety.
• Make pragmatic architectural trade offs across latency, cost, accuracy, scalability, and maintainability.
• Integrate and operate LLMs (commercial and/or open source) including model selection, fine tuning strategies, embeddings, retrieval (RAG), and inference optimization.
• Address real world issues: hallucinations, drift, prompt regressions, failure modes, and customer trust.
• Deploy and operate AI services across cloud platforms (AWS, Azure, GCP), including secure enterprise integrations and customer specific deployments.
• Ensure the platform is shippable, debuggable, and supportable — not fragile or research grade.
• Act with strong ownership: identify gaps, propose solutions, and move forward without waiting for perfect requirements.
• 6+ years of professional software development experience, with significant time shipping B2B products used by external customers.
• Strong software engineering foundation with expert level Python and experience designing production systems.
• Proven experience building, deploying, and operating AI powered products in production,
• Hands on experience with LLMs and GenAI systems in real applications (e.g., agents, copilots, automation, decision systems).
• Understanding of at least several of the following:
• Agent frameworks and orchestration
• Prompt engineering and tool use patterns
• RAG architectures and vector search
• Model evaluation, feedback loops, and monitoring
• Safety, guardrails, and enterprise controls
• Hands on experience with multiple of the following in real systems:
• LangGraph and/or LangChain
• LlamaIndex
• Vector databases (e.g., Pinecone, Weaviate, FAISS, Milvus)
• Prompt engineering as a managed, versioned, testable artifact
• Experience deploying and operating LLMs using:
• AWS SageMaker, Vertex AI, or equivalent managed platforms
• Direct API integrations (OpenAI, Anthropic)
• Experience designing multi agent systems or complex agent workflows.
• Experience commercializing AI features under enterprise constraints (security, compliance, uptime).
• Comfort operating in ambiguity and making decisions with incomplete information.
• Contributions to open source GenAI tooling or internal frameworks used at scale.
• Experience with supervised fine tuning, parameter efficient tuning methods (LoRA, QLoRA), reinforcement learning (RLHF) and preference optimization (PPO, DPO, GRPO).
• Experience deploying LLMs at scale (Kubernetes, model serving, GPU optimization).

Our commitment to you!