BeaconFire Inc.
Gen AI Engineer
⭐ - Featured Role | Apply direct with Data Freelance Hub
This role is for a Gen AI Engineer with a contract length of "unknown," offering a pay rate of "unknown." Work location options include Southfield, MI, Princeton, NJ, San Francisco, CA, Santa Clara, CA, St. Louis, MO, or Austin, TX. Key skills required are proficiency in LangChain/LlamaIndex, cloud LLM providers, Python, and experience in building RAG pipelines and prompt engineering.
🌎 - Country
United States
💱 - Currency
$ USD
-
💰 - Day rate
Unknown
-
🗓️ - Date
October 8, 2025
🕒 - Duration
Unknown
-
🏝️ - Location
Unknown
-
📄 - Contract
Unknown
-
🔒 - Security
Unknown
-
📍 - Location detailed
Princeton, NJ
-
🧠 - Skills detailed
#Azure #Cloud #Langchain #AWS (Amazon Web Services) #Security #AI (Artificial Intelligence) #Monitoring #Airflow #Observability #Python
Role description
GenAi Engineer
Southfield, Michigan/Princeton, NJ/San Francisco, CA/Santa Clara, CA/St. Louis, MO/Austin, TX
The project is focused on building production-grade GenAI solutions with emphasis on:
• RAG pipelines leveraging LLMs
• Prompt engineering (system/tool prompts, function calling, versioning with evals)
• Evaluation & observability (ground truth setup, confusion metrics, LLM-as-judge with human review, cost & latency monitoring)
• Retrieval strategies & prompt patterns (context management, hallucination mitigation)
• LangChain/LlamaIndex (or equivalent) proficiency
• Cloud LLM providers (Azure OpenAI, AWS Bedrock, Vertex AI)
• Workflow orchestration (Airflow, Dagster)
• Security & privacy (PII handling, RBAC)
• Python expertise with strong practical experience
Success criteria:
• A production-ready prompt + RAG pipeline system with measurable quality lift (accuracy/confusion metrics) and reduced hallucinations, backed by a repeatable evaluation harness.
GenAi Engineer
Southfield, Michigan/Princeton, NJ/San Francisco, CA/Santa Clara, CA/St. Louis, MO/Austin, TX
The project is focused on building production-grade GenAI solutions with emphasis on:
• RAG pipelines leveraging LLMs
• Prompt engineering (system/tool prompts, function calling, versioning with evals)
• Evaluation & observability (ground truth setup, confusion metrics, LLM-as-judge with human review, cost & latency monitoring)
• Retrieval strategies & prompt patterns (context management, hallucination mitigation)
• LangChain/LlamaIndex (or equivalent) proficiency
• Cloud LLM providers (Azure OpenAI, AWS Bedrock, Vertex AI)
• Workflow orchestration (Airflow, Dagster)
• Security & privacy (PII handling, RBAC)
• Python expertise with strong practical experience
Success criteria:
• A production-ready prompt + RAG pipeline system with measurable quality lift (accuracy/confusion metrics) and reduced hallucinations, backed by a repeatable evaluation harness.
