Experience:

• 5+ years of Python engineering experience with production REST API development using FastAPI or Flask
• 2+ years of hands-on LLM application development using LangChain, LlamaIndex, or LangGraph shipped to production

Responsibilities:

• Embed with client product and engineering teams to architect and ship production-grade LLM-powered features end-to-end
• Build and optimize RAG pipelines with advanced chunking strategies, hybrid search, re-ranking, and vector database management
• Develop multi-agent systems and autonomous workflows with tool use, self-correction, and complex task execution
• Fine-tune open-source LLMs using LoRA/QLoRA and implement 4-bit/8-bit quantization for cost-effective deployment
• Set up and maintain production AI infrastructure including model serving, containerized deployments, and continuous evaluation pipelines
• Implement AI safety and guardrail layers to mitigate hallucinations, enforce PII data protection, and monitor token usage and inference costs
• Transform raw, unstructured client data into high-value AI features in collaboration with client-side Data Engineering and Product teams

Additional responsibilities:

• Collaborate closely with client-side product and data engineering stakeholders
• Drive architectural decisions independently within client AI product teams

Nice to have:

• Prior experience in client-facing or consulting delivery model for AI solutions
• Experience building multi-agent systems using CrewAI, AutoGPT, or custom function-calling/tool-use architectures
• Familiarity with AI safety frameworks, PII redaction pipelines, or responsible AI governance practices at enterprise level
• Exposure to supply chain, ERP, or data platform modernization use cases
• AWS or GCP professional-level certification

More skills:

hybrid search, re-ranking, vector database management, Pinecone, Milvus, Qdrant, ChromaDB, multi-agent systems, autonomous workflows, LLaMA, LoRA, QLoRA, 4-bit quantization, 8-bit quantization, Hugging Face Transformers, PyTorch, Docker, Kubernetes, AWS Bedrock, Google Vertex AI, LangSmith, Weights & Biases, Arize Phoenix

Other:

• Full-time position
• Industry: Information Technology & Services, Management Consulting
• Company founded in 2020, headquartered in Tampa, Florida
• Over 450 professionals across seven global offices in more than 25 countries
• Company specializes in AI-driven digital transformation, platform engineering, data analytics, supply chain transformation, and digital customer experience solutions
• Company expanded product engineering capabilities through strategic acquisition in 2023
• Fast-paced, ownership-driven environment with enterprise scale delivery
• Hybrid work model with flexibility for remote work and structured in-office collaboration
• Direct ownership of AI features shipping into live enterprise client products
• Global collaboration across seven offices with exposure to diverse enterprise domains and client challenges