Software Engineer 3

What You'll Do

Define technical vision and architecture: Lead the design and architecture of scalable, production-grade GenAI systems using LangChain, LangGraph, FastAPI, and modern AI frameworks. Make critical technical decisions that balance innovation, scalability, and maintainability

Drive GenAI innovation: Research, prototype, and implement cutting-edge GenAI techniques including advanced prompt engineering, RAG optimization, agentic AI systems, fine-tuning, and multi-agent orchestration

Lead AI experimentation and evaluation: Design and implement comprehensive evaluation frameworks for LLM performance, establish best practices for prompt engineering, and drive data-driven decision making through rigorous experimentation

Own GenAI at utility and program scale: Architect and optimize LLM workloads that support millions of calls across multiple utilities and channels, under strict cost and latency targets.

Architect event-driven AI systems: Design and implement sophisticated event-driven architectures using SQS, asynchronous workflows, distributed processing, and microservices patterns

Establish GenAI best practices: Define and enforce coding standards, design patterns, testing strategies, and operational excellence for GenAI applications. Champion observability, monitoring, and reliability

Technical leadership and mentorship: Mentor and guide engineers across all levels, conduct architecture reviews, provide technical direction, and foster a culture of continuous learning and innovation

Cross-functional collaboration: Partner with product management, data science, engineering leadership, and business stakeholders to translate business requirements into technical solutions. Communicate complex technical concepts to diverse audiences

Drive strategic initiatives: Identify opportunities for AI-driven innovation, evaluate emerging technologies, and lead proof-of-concept projects that align with business objectives Ensure production excellence: Establish SLAs, implement monitoring and alerting, optimize performance and cost, and ensure high availability of AI services

Thought leadership: Represent Bidgely in the GenAI community through technical blogs, conference talks, open-source contributions, and industry engagement

What Makes You Successful

Education: BS/MS+ in Computer Science, AI/ML, or equivalent from premier institutes

Experience: 5+ years of software engineering experience with at least 1-2 years focused on Generative AI, Agentic AI, and production LLM-based applications

Expert-level knowledge of LangChain, LangGraph, and LLM orchestration frameworks; deep understanding of prompt engineering, RAG architectures, agentic AI, and multi-agent systems

Production AI Systems: Proven track record of architecting and deploying production-grade AI systems at scale, handling millions of requests and complex workflows

API & Microservices: Extensive experience building scalable RESTful APIs, microservices architectures, and event-driven systems using FastAPI, Flask, or similar frameworks LLM Integration: Deep expertise integrating and optimizing LLM providers; understanding of model selection, cost optimization, and latency management

Technical Leadership: Demonstrated ability to lead technical teams, drive architectural decisions, and mentor engineers; experience with code reviews, technical design documents, and cross-team collaboration

Problem Solving: Exceptional problem-solving skills with ability to tackle ambiguous, complex challenges; strong in algorithms, data structures, and system design

Communication: Outstanding communication skills; ability to influence technical direction, present to leadership, and collaborate effectively across global distributed teams

Preferred Qualifications

Python & Architecture: Expert-level Python programming with deep knowledge of software architecture, design patterns, distributed systems, and performance optimization

Experience with vector databases (ChromaDB, Pinecone, Weaviate, FAISS) and advanced retrieval techniques

Deep knowledge of LLM observability tools (LangSmith, Langfuse, Weights & Biases) and evaluation frameworks

Expertise in AWS services (Bedrock, SQS, S3, Lambda, ECS, Parameter Store) and cloud-native architectures

Experience with fine-tuning, RLHF, prompt optimization techniques, and model evaluation methodologies

Knowledge of PostgreSQL optimization, Redis caching strategies, and database performance tuning

Experience with Docker, Kubernetes, Terraform, and infrastructure-as-code

Background in building conversational AI, chatbots, or virtual assistants

Experience with MLOps, model deployment pipelines, and A/B testing frameworks

Familiarity with emerging AI trends: multi-modal models, reasoning models, agent frameworks

Interested candidates can share their resume with : [Confidential Information]