---
title: "Senior Applied AI Engineer, Mission-Critical Agents"
slug: "senior-applied-ai-engineer-mission-critical-agents"
id: "98594e48-3f02-44db-8bcd-dccc6dbb06f7"
department: "Applied AI"
department_code: "APP"
location: "New York, NY"
workplace_type: "Hybrid"
employment_type: "Full-time"
compensation: "$200k – $280k (annual package)"
is_remote: false
is_featured: false
headcount: 1
canonical_url: "https://jobs.talent247.co/jobs/senior-applied-ai-engineer-mission-critical-agents"
markdown_url: "https://jobs.talent247.co/jobs/senior-applied-ai-engineer-mission-critical-agents.md"
apply_endpoint: "https://jobs.talent247.co/api/public/jobs/senior-applied-ai-engineer-mission-critical-agents/apply"
schema_endpoint: "https://jobs.talent247.co/api/public/jobs/senior-applied-ai-engineer-mission-critical-agents/form-schema"
webmcp_tool: "apply_for_role"
updated_at: "2026-11-15T17:34:00.502Z"
content_signal: "search=yes, ai-input=yes, ai-train=no"
---

# Senior Applied AI Engineer, Mission-Critical Agents

## Position Telemetry

- **Reference:** `SENIOR-APPLIED-AI-`
- **Practice / Sector:** Applied AI (`APP`)
- **Location:** New York, NY
- **Workplace Type:** Hybrid
- **Employment Type:** Full-time
- **Compensation:** $200k – $280k (annual package)
- **Canonical HTML URL:** https://jobs.talent247.co/jobs/senior-applied-ai-engineer-mission-critical-agents

## Role Dossier & Specification

THE CLIENT & MANDATE
Our client is a leading US AI platform and data infrastructure company headquartered in San Francisco with a rapidly growing Applied AI hub in New York City. Their Mission-Critical Agents division builds auditable, multi-agent decision-support and operational planning systems deployed inside high-consequence federal, defense, financial, and global logistics environments where hallucinations or unauthorized actions are unacceptable.

They have retained Talent247 to hire a Senior Applied AI Engineer for Mission-Critical Agents in New York, NY. Working directly with domain operators and core platform teams, the appointed engineer will build retrieval-grounded agent runtimes, deterministic verification guardrails, and portable self-hosted inference stacks capable of running across commercial clouds and air-gapped enclaves.

KEY RESPONSIBILITIES
• Architect stateful, multi-step agentic workflows combining hybrid multimodal retrieval, structured tool execution, human-in-the-loop approval gates, and immutable cryptographic audit logs.
• Engineer zero-hallucination citation verification and schema-constrained decoding pipelines over heterogeneous intelligence reports, satellite/imagery metadata, financial filings, and operational databases.
• Build portable, cloud-agnostic model-serving and orchestration stacks (Kubernetes, vLLM, quantized open-weight models) deployable cleanly into VPC-isolated and air-gapped environments.
• Develop offline simulation replay harnesses and domain-specific regression suites that test agent robustness under degraded, contradictory, or adversarial input streams.
• Fine-tune task-specialized tool-calling and reranking models to achieve frontier-grade reasoning accuracy within strict latency and on-prem GPU footprints.
• Partner with customer mission leads in NYC and Washington, D.C. to translate high-stakes operational workflows into resilient production AI software.

TECHNICAL ENVIRONMENT & OFFERING
Stack: Python, TypeScript, Go, PyTorch, vLLM/TensorRT-LLM, PostgreSQL/pgvector, OpenSearch, Temporal, Kubernetes, AWS/GovCloud/on-prem GPU clusters. Workplace: Hybrid in New York, NY. Compensation: $200,000 – $280,000 base salary plus equity grants, comprehensive healthcare, and 401(k).

## Core Requirements

ESSENTIAL QUALIFICATIONS
• 5+ years of software and applied ML engineering experience building production backend systems and LLM/agent applications at scale.
• Deep hands-on expertise in agentic orchestration (tool-use state machines, durable execution, context engineering), hybrid RAG, and structured output verification.
• Practical experience deploying and optimizing open-weight LLMs/VLMs via vLLM, SGLang, or TensorRT-LLM inside Kubernetes environments.
• Strong full-lifecycle engineering rigor in Python and TypeScript or Go, including observability, RBAC security enforcement, and automated evaluation gating.
• US work authorization (US citizenship or permanent residency advantageous for select regulated customer engagements, though commercial tracks are also open).

PREFERRED / BONUS EXPERIENCE
• Experience deploying software into air-gapped, FedRAMP/IL4+, or highly regulated financial services environments.
• Hands-on experience fine-tuning LoRA adapters or domain rerankers (SFT/DPO) on specialized technical or geospatial corpora.
• Familiarity with Temporal workflow orchestration, Model Context Protocol (MCP) servers, and OpenTelemetry agent tracing.

## Application Schema & Direct Apply (`apply_for_role`)

Candidates and authorized AI agents on behalf of a candidate can submit an application via the declarative WebMCP form tool `apply_for_role` on https://jobs.talent247.co/jobs/senior-applied-ai-engineer-mission-critical-agents or via HTTP `POST https://jobs.talent247.co/api/public/jobs/senior-applied-ai-engineer-mission-critical-agents/apply` (`application/json` or `multipart/form-data`). Non-browser HTTP agents must include header `X-Talent247-Intake-Token` obtained from `GET https://jobs.talent247.co/api/public/intake-token` (or automatically returned in `GET https://jobs.talent247.co/api/public/jobs/senior-applied-ai-engineer-mission-critical-agents/form-schema`).

### Form Fields

- `full_name` (text, required): Full name
- `email` (email, required): Email
- `phone` (phone, optional): Phone
- `location` (text, optional): Location
- `linkedin_url` (url, optional): LinkedIn URL
- `cover_letter` (textarea, optional): Cover letter
- `consent` (checkbox, required): I consent to my data being processed for this application
- `cv_file` / `cv_base64` + `cv_filename`: Upload a CV in .pdf or .docx format (<= 10 MB) or provide an `https://` LinkedIn profile URL in `linkedin_url`.

### Alternative: Talent Pool Intake (`join_talent_pool`)

If this mandate is not an exact match, register once in the Talent247 Talent Pool at https://jobs.talent247.co/talent-pool (`https://jobs.talent247.co/talent-pool.md`) via WebMCP tool `join_talent_pool` or `POST https://jobs.talent247.co/api/public/talent-pool`.
