Agentic/Gen AI Architect

Infojini Inc; Washington; Hybrid; USD 140,000 - 170,000; Full time

Job summary

Infojini Inc. is seeking a Forward Deployed Engineer (FDE) who blends software and data engineering with hands-on Generative AI expertise to solve customer challenges.

You will translate ambiguous requirements into working technical solutions, build API integrations and ETL pipelines, and deploy AI-powered workflows across environments. Hybrid work from the Washington, DC metro area is expected.

Qualifications

• Hands-on software engineering experience.

Responsibilities

• Build and deploy customer-facing AI solutions hands-on.
• Collaborate with customers to translate complex problems into technical architectures.
• Design and integrate REST APIs and backend services for end-to-end workflows.
• Prototype and deploy GenAI-powered applications and AI agent workflows.
• Own technical delivery from discovery through production adoption.
• Develop ETL/ELT pipelines and data integrations for customer data.
• Write production-grade code (Python/TypeScript) and follow best practices.
• Engage with customers and stakeholders in fast-moving environments.

Skills

Software engineering

Data engineering

API design

Generative AI

AI agents

Requirements translation

Debugging

Communication

Customer facing

Tools

Cloud platforms (AWS/Azure/GCP)

Snowflake

Databricks

Spark

Kafka

Airflow

dbt

Job description

Employment Type: Full Time

About the Role

We are looking for a Forward Deployed Engineer (FDE) who combines strong software and data engineering fundamentals with hands‑on Generative AI expertise and exceptional customer‑facing skills.

This is not a traditional implementation, solutions consulting, or data engineering role. The FDE will work directly with customers to understand complex and often ambiguous operational problems, translate them into technical solutions, and then build and deploy those solutions hands‑on.

You will operate at the intersection of customers, data, software engineering, and Generative AI. One engagement might require building an API integration and ETL pipeline; another might involve creating an AI agent that automates an operational workflow; another could require rapidly prototyping a customer‑specific application using LLMs and enterprise data.

We are looking for someone who is comfortable moving between a customer conversation, architecture whiteboard, IDE, data pipeline, and production deployment.

What We’re Looking For

Must Have

• Strong hands‑on software engineering experience.
• Strong data engineering fundamentals, including ETL/ELT, data modeling, schema mapping, and data pipelines.
• Experience designing and integrating REST APIs and backend services.
• Hands‑on experience building applications using LLMs / Generative AI.
• Experience building at least some of: AI agents, RAG systems, tool‑calling workflows, LLM‑powered applications, or AI workflow automation.
• Ability to take an ambiguous customer requirement and independently turn it into a working technical solution.
• Strong debugging and problem‑solving skills across applications, APIs, infrastructure, and data.
• Excellent written and verbal communication skills.
• Demonstrated ability to work directly with customers and senior stakeholders.
• Ability to operate effectively in fast‑moving environments with incomplete requirements.
• Based in or willing to work from the Washington, DC metro area.
• Ability to work in a hybrid environment with office/customer‑site presence at least 2–3 days per week.

Strongly Preferred

• Experience working as a Forward Deployed Engineer, Solutions Engineer, Solutions Architect, Technical Consultant, or customer‑facing Software/Data Engineer.
• Experience supporting the federal government, defense, intelligence, national security, or other mission‑critical environments.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Experience with modern data platforms and technologies such as Snowflake, Databricks, Spark, Kafka, Airflow, dbt, or equivalent technologies.
• Experience with vector databases, embeddings, retrieval systems, and modern LLM application frameworks.
• Experience deploying AI applications into production environments.
• Experience designing human‑in‑the‑loop workflows and AI evaluation systems.
• Familiarity with enterprise security, authentication, authorization, and data‑governance requirements.
• Demonstrated ability to develop reusable technical approaches and influence engineering or product strategy.
• Work directly with customers to understand business objectives, operational workflows, technical environments, and pain points.
• Translate ambiguous customer requirements into concrete technical architectures and working solutions.
• Rapidly prototype, build, test, deploy, and iterate on customer‑facing solutions.
• Own technical delivery from initial discovery through implementation and production adoption.
• Make pragmatic engineering decisions balancing speed, scalability, security, maintainability, and customer impact.
• Identify technical risks, data‑quality issues, integration constraints, and implementation trade‑offs early.
• Write production‑quality code, primarily using languages such as Python and/or TypeScript.
• Design and develop APIs and backend services.
• Integrate applications with databases, APIs, cloud services, AI models, and customer systems.
• Build lightweight applications and interfaces where needed to deliver an end‑to‑end customer solution.
• Apply sound software engineering practices around testing, version control, CI/CD, monitoring, security, and documentation.
• Design and implement ETL/ELT pipelines for ingestion, extraction, transformation, and delivery workflows.
• Execute bulk data processing and deliver data products in formats including Parquet, CSV, JSON, and related formats.
• Build, configure, test, and maintain REST/API integrations for customer and internal use cases.
• Design and build GenAI‑powered applications that automate complex customer workflows.
• Build LLM‑based agents and agentic workflows capable of reasoning across enterprise data, APIs, and tools.
• Develop RAG pipelines connecting LLMs with structured and unstructured enterprise data.
• Implement tool/function calling, structured outputs, workflow orchestration, and multi‑step AI systems.
• Build evaluation frameworks and feedback loops to measure and improve AI application quality.