AI Software Engineer - Senior
# AI Software Engineer - Senior **FSS Government Solutions** · Remote · `Remote` 🕒 **Статус:** *Опубликовано: вчера* · *Источник: Indeed* --- ### About the Role FSS Government Solutions is seeking a Senior Python Developer to design and deliver cloud-native, event-driven backend platforms across Microsoft Azure and Amazon Web Services , including platforms that host and operate AI-enabled products. You will own architecture and implementation of high-reliability workflows, integrate internal and external systems at scale, distribute metadata and events under SLA, and optimize service design for LLM access, retrieval, cost, latency, and reliability. You will provide technical leadership on production Python services and on the interfaces that connect those services to models and agent tooling in a dual-cloud environment. - Role is 100% Remote - Candidates must obtain a Public Trust Clearance What you will do - Lead design and implementation of cloud-native, event-driven platforms that integrate many independent systems into a unified operational ecosystem spanning Azure and AWS. - Architect durable, event-driven workflows using Azure Durable Functions / Service Bus / Event Grid and AWS Step Functions / EventBridge / SQS / SNS to orchestrate high daily event volumes with reliability, retries, and recovery. - Build Python backend services that generate and distribute structured metadata and events to downstream consumers under tight availability SLAs, including near-real-time propagation targets, regardless of which cloud owns a given path. - Design scalable, fault-tolerant microservice-style components that can be extended or moved between clouds without rewriting the platform. - Integrate internal and third-party systems through REST and GraphQL; use Azure API Management and/or Amazon API Gateway as governed gateways. - Design and implement AI product architecture on both clouds: model-serving and inference paths (Azure OpenAI / Azure AI Foundry and Amazon Bedrock), retrieval / grounding pipelines, prompt-and-tool orchestration, and secure service interfaces for LLM interaction. - Build MCP-style and function-calling interfaces so agents and LLMs can invoke platform APIs safely (auth, scoped tools, timeouts, audit). - Optimize AI workloads for production: token and compute cost, latency budgets, rate limits, caching, fallback models across providers, and evaluation / tracing of model calls. - Implement durable storage with Azure Blob / Table Storage and Amazon S3 / DynamoDB for event-driven exchange, recovery, embeddings or document corpora, and audit of AI and integration traffic. - Establish observability across application and AI paths: structured logging, distributed tracing, prompt/tool telemetry, and alerting in Application Insights and CloudWatch / X-Ray (or an equivalent unified telemetry layer). - Define cloud-portable patterns (interfaces, adapters, IaC) so services are not hard-wired to a single vendor’s SDK. - Influence architecture, raise code quality, and mentor engineers on backend, dual-cloud, and AI-integration patterns. - Translate stakeholder requirements into production-ready designs and incremental delivery. Required qualifications - Professional software engineering experience as a senior or lead engineer on production backend platforms in Azure and AWS (hands-on in both, not awareness of one). - Strong Python 3.11+ for production services (async APIs, packaging, typing, testing). - Hands-on Azure: Functions, Durable Functions, Service Bus, Event Grid, Blob Storage, Table Storage, API Management, App Services / Container Apps, Key Vault, App Configuration. - Hands-on AWS: Lambda, Step Functions, EventBridge, SQS/SNS, S3, DynamoDB and/or RDS, API Gateway, Secrets Manager / SSM, IAM. - Proven event-driven and distributed-systems design (orchestration, pub/sub, idempotency, failure handling) across more than one cloud. - Experience optimizing architecture for AI products in production: integrating LLMs (Azure OpenAI and/or Amazon Bedrock), designing tool/API access for models, and addressing cost, latency, reliability, and security of model use. - REST and GraphQL integration experience; comfort with API gateways in at least one cloud. - Relational data access (SQL Server, PostgreSQL, or equivalent) via SQLAlchemy, async drivers, or similar. - Observability in production (Application Insights and/or CloudWatch / X-Ray), including visibility into downstream AI calls. - CI/CD with Azure DevOps and/or AWS-native pipelines (CodePipeline / GitHub Actions) using YAML or equivalent IaC-friendly pipelines. - Ability to lead technical decisions and work directly with product and business stakeholders. Preferred qualifications - FastAPI, Django, or equivalent for service APIs; Pydantic for contracts and validation. - Dual-provider LLM use behind APIM / API Gateway: Azure OpenAI / Foundry and Amazon Bedrock (Claude, Llama, Nova, OpenAI-on-Bedrock, or similar). - Microsoft Agent Framework (Python), LangGraph / LangChain, MCP servers, tool-calling, function-calling, or agent-orchestration patterns in production or serious pilots. - RAG: document ingestion, chunking, embeddings, vector or hybrid search (Azure AI Search, OpenSearch, or equivalent), grounding and citation. - AI evaluation, red-teaming, or quality gates (offline eval sets, online traces, hallucination / tool-failure handling). - SCTE-224 or other broadcast / media metadata standards. - Clean Architecture, DDD, or behavior-driven design in production services. - Terraform, Bicep, or CDK for dual-cloud infrastructure. - Containers and orchestration: Azure Container Apps / AKS and ECS / EKS. - C#, JavaScript, or PowerShell for automation and integration with existing services. - Multi-tenant or large-scale enterprise backends. - B.S. in Computer Science or equivalent experience. Core skills Python 3.11+, FastAPI (or equivalent), SQLAlchemy / SQL, Azure Functions / Durable Functions, Service Bus, Event Grid, APIM, Blob/Table Storage, Key Vault, Application Insights, AWS Lambda, Step Functions, EventBridge, SQS/SNS, S3, DynamoDB, API Gateway, IAM, CloudWatch, Azure DevOps / GitHub Actions YAML, REST, GraphQL, Azure OpenAI / Amazon Bedrock, MCP and tool-calling interfaces, RAG / retrieval pipelines, event-driven architecture, dual-cloud adapters, microservices, AI cost and latency optimization. Pay: $200,000.00 - $210,000.00 per year Experience: - AI: 2 years (Required) - python : 4 years (Required) Work Location: Remote
Наблюдалась 2026-09-29, впервые 2026-09-28, источник — Indeed.